To address the challenge of predicting mechanical properties due to the unavoidable and multi-characteristic nature of defects in additive manufacturing lattice structures, an improved ensemble learning prediction model is proposed. The objective is to predict the true value of the yield stress of the lattice structure by using the data obtained from finite element simulation. The prediction model is constructed using the diversity and randomness of defects in the lattice structure as the input features of the model and the yield stress as the output. In order to improve the prediction capability of the model for multi-defect features, the Boosting module is added to the stacking model. To further improve the data-defect fit capability, feature transformation and feature combination methods are used to increase the number of data features, which in turn enhances the generalization performance of the model. In addition, the model has the ability to analyze the effect of defect characteristics and distribution on stress. The experimental structure shows that the model proposed in this paper can predict the yield stress of defects in defective lattice structures with an $R^2$ of 0.844. The proposed model reduces the time required for preparation and the cost of testing while ensuring prediction accuracy and enabling small samples of simulation data to predict true values. The research idea of this paper provides a research basis for industrial inspection and evaluation of lattice structures used in additive manufacturing.

为了解决由于增材制造晶格结构中不可避免的缺陷和多特征缺陷而预测机械性能的挑战，改进的集成学习提出了预测模型。目的是利用有限元模拟获得的数据来预测晶格结构屈服应力的真实值。利用晶格结构中缺陷的多样性和随机性作为模型的输入特征，以屈服应力作为输出来构建预测模型。为了提高模型对多缺陷特征的预测能力，在Stacking模型中加入Boosting模块。为了进一步提高数据缺陷拟合能力，采用特征变换和特征组合方法来增加数据特征数量，从而增强数据缺陷拟合能力。模型的泛化性能。此外，该模型还能够分析缺陷特征和分布对应力的影响。实验结构表明，本文提出的模型可以预测缺陷晶格结构中缺陷的屈服应力。${右}^2$0.844。所提出的模型减少了准备所需的时间和测试成本，同时确保了预测精度并使小样本的模拟数据能够预测真实值。本文的研究思路为增材制造中晶格结构的工业检测和评估提供了研究基础。